KI-Coding-Tools Changelog Hub

Claude Codev2.1.245Neu

Claude Code 2.1.245

25. August 2026

• •Fixed a crash on startup on Linux distributions that ship glibc 2.44 (for example Arch Linux, CachyOS and Fedora Rawhide)

Claude Codev2.1.243Neu

Claude Code 2.1.243

24. August 2026

• •Added a Loops breakdown to /usage: per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty /loop tasks are easy to spot
• •Added modelPicker setting: curate the /model picker with an ordered, labeled list of models (any id spelling, including Vertex/Bedrock ids), appended to or replacing the built-in lineup
• •Added promptCacheTtl and subagentPromptCacheTtl settings so API-key and cloud-provider users can keep a 1-hour prompt cache on the main conversation while subagents stay at 5 minutes
• •Added modelPricing managed setting so an organization's contracted per-model rates and discount multiplier are used for /cost, the status line, and telemetry cost figures instead of list price
• •Added a keyless sign-in under /login → Anthropic Console: "Sign in with your Console account" (recommended) alongside creating an API key, so organizations that don't allow API keys can sign in
• •Added a Skipped sources line to /status that lists managed settings sources (for example managed-settings.json) present but not applied because a higher-precedence managed source is active
• •Added a managed marker in /mcp and /plugins on claude.ai connectors whose authentication is managed by your organization
• •Added a tip pointing claude.ai users who haven't connected GitHub for Claude Code on the web to /web-setup
• •Added a /status line showing whether GitHub is connected for Claude Code on the web (Pro/Max), pointing to /web-setup when it isn't
• •Added the model (and effort level) each subagent ran on to /tasks and the agent detail dialogs
• •Fixed remote MCP servers in non-interactive (-p) and SDK sessions never recovering after a dropped connection; they now reconnect automatically or report as failed
• •Fixed MCP server sign-in started from the desktop app failing with "Invalid redirect URI" on servers that support client ID metadata documents (for example Linear)
• •Fixed auto mode staying unavailable at startup when a temporary server-side disable was cached and later flag fetches failed
• •Fixed auto mode tool calls being denied as "temporarily unavailable" after about a minute of waiting when the API was briefly overloaded and asked the client to retry
• •Fixed the /model picker silently ignoring an Ultracode selection; picking Ultracode now applies it to the current session
• •Fixed /resume only listing the 50 most recent sessions; the picker now loads more as you scroll
• •Fixed cloud sessions resuming after a mid-turn restart with a pending hook or background-task notification re-sent as the prompt instead of the normal continuation message
• •Fixed cross-session messaging silently turning off inside user namespaces and rootless containers after the 2.1.232 socket-directory hardening
• •Fixed text that hangs outside its container (for example the sign-in URL in /login) losing its leading columns when another part of the screen repaints
• •Fixed spellcheck not underlining a misspelled word typed directly after an emoji
• •Fixed background subagents not waking when their last background Bash task completes
• •Fixed sessions going silent for 10+ minutes when the Anthropic API never starts a response: the request now times out after ~3 minutes, retries once, then shows API Error: No response from API
• •Fixed auth, model-availability, and other client-generated error messages rendering like model output instead of as error lines
• •Fixed workload identity federation in CI: processes in one job share the exchanged token instead of re-exchanging the single-use token; a rejected exchange fails fast with the server's message
• •Fixed server-managed companyAnnouncements not showing at startup in a session that began with signing in (for example the first launch after /logout)
• •Fixed hook if conditions like Bash(cat *) firing on unrelated Bash commands when the command contained $() or backtick command substitution followed by more arguments
• •Fixed plugin dependencies declared with a marketplace field never resolving when both plugins are loaded together via --plugin-dir
• •Fixed /reload-plugins keeping the LSP tool after the last LSP plugin is disabled; it now also warns before an LSP plugin change that would re-read the conversation
• •Fixed --agents silently ignoring invalid JSON or invalid agent definitions; it now exits with a clear error, like --mcp-config
• •Fixed /status showing "Found invalid entries in: ." with no filename when ~/.claude.json has an invalid MCP server entry
• •Fixed /clear removing the /rename session name from the prompt bar even though the name was kept for the new session
• •Fixed Ctrl+R history search and up-arrow history breaking when ~/.claude/history.jsonl contains a malformed entry
• •Fixed Ctrl+[ not leaving vim INSERT mode in terminals that encode modified keys (modifyOtherKeys / kitty protocol)
• •Fixed the local IDE connection being routed through HTTPS_PROXY (and sometimes failing) when localhost was listed in NO_PROXY but not lowercase no_proxy; both casings are now honored
• •Fixed sandbox network-violation details being dropped from the Bash tool result when the blocked command still exited 0 (for example curl printing the proxy's 403 page)
• •Fixed the status line rate_limits fields and /usage still showing a rate-limit window's pre-reset usage percentage after the window reset while the session was idle
• •Fixed claude --teleport <session> exiting on uncommitted changes instead of offering to stash them and continue, as the session picker already does
• •Fixed /web-setup repeatedly asking you to log in when an older GitHub CLI (without gh auth token) was already authenticated
• •Fixed Claude in Chrome losing its connection to Claude Code after an auto-update cleaned up the version it was set up with; the native host now launches via the stable claude launcher
• •[VSCode] Fixed sessions started before feature flags were first fetched (for example right after install) opening in the default permission mode instead of auto mode or your configured default mode
• •[VSCode] Fixed Focus view sections you expanded collapsing on their own during subagent tool activity
• •Improved startup time: sandbox and MCP bring-up no longer block the first frame, bare launches skip subcommand registration, and workflow discovery, settings, and trust-store work is cheaper
• •Improved native install and auto-update download size: the binary is now zstd-compressed (about 75 MB instead of 340 MB on Linux x64)
• •Improved attribution of usage telemetry to your organization for sessions that authenticate with ANTHROPIC_AUTH_TOKEN directly against the Anthropic API, so its data-handling settings apply
• •Improved native binary size: about 2 MB smaller by storing the bundled skill and prompt text more compactly
• •Improved memory usage of native builds: code is now loaded on demand instead of keeping the whole bundle resident (roughly 40–70 MB less memory per session)
• •Improved peak memory usage in long-running sessions (the runtime now garbage-collects sooner as the heap grows)
• •Improved /login over SSH: the sign-in URL appears immediately, pressing c reports how the URL was copied instead of always claiming success, and a hint explains how to select text in fullscreen
• •Improved the error when effort xhigh/max is used with thinking turned off: it now names the level, the setting that disabled thinking, and /effort high as the fix
• •Improved /loop: consecutive wake-ups where Claude has nothing to do now fold into a single line in the terminal instead of printing each one
• •Changed the sandboxed Bash tool prompt to no longer list allowed network hosts, so Claude attempts requests (and you can approve new hosts) instead of assuming unlisted hosts are blocked
• •Updated the /model picker and the bundled claude-api skill to show Sonnet 5's $2/$10 per Mtok pricing as its standard list price rather than a limited-time promo
• •Changed computer use on macOS so clicking the desktop, Dock, or a Finder window requires granting Finder via the access dialog, like any other app
• •Changed /model, /fast, and /effort to also run immediately instead of queueing until the turn ends on Bedrock, Vertex, and Foundry and when telemetry is disabled
• •Fixed claude remote-control exiting and stranding attached Remote Control sessions when the server drops its environment mid-session; it now recovers
• •Fixed Remote Control sessions served by claude remote-control sometimes getting stuck after it was stopped and restarted, for Team and Enterprise members without an admin or owner role
• •Changed the cross-session messaging inbox socket to close connections that send no complete line within 30 seconds; scripts posting to it should connect once their data is ready
• •Improved the notice when resuming a conversation whose Remote Control is held by another terminal: it now says sessions on other machines can't be seen from, or reach, this one
• •[VSCode] Improved history trimming in long sessions: older tool-activity rows are dropped first so your messages and Claude's replies stay visible
• •[VSCode] Improved attribution of the extension's own usage telemetry to your organization when you are signed in with a Claude account, so its data-handling settings apply

Claude Codev2.1.241Neu

Claude Code 2.1.241

22. August 2026

• •Bug fixes and reliability improvements

Claude Codev2.1.240Neu

Claude Code 2.1.240

22. August 2026

• •Bug fixes and reliability improvements

Claude Codev2.1.239Neu

Claude Code 2.1.239

21. August 2026

• •Cost estimates (/cost, status line, --max-budget-usd) now include the 1.1× US-only-inference premium for data-residency workspaces
• •Added the one-time fullscreen renderer offer on Bedrock, Vertex, Foundry and other previously excluded setups; new installs there now start in fullscreen
• •Added /claude-api upgrade to migrate Python projects from anthropic 0.x to 1.x, and updated the skill's Python reference for 1.x (timeouts use anthropic.Timeout, not httpx.Timeout)
• •Cloud sessions: plugins synced from claude.ai now show as name@synced, work with claude plugin enable/disable <name>@synced, and never override a same-named plugin you installed
• •Alpine/musl builds: native image paste, clipboard, and audio-capture add-ons now load (musl-built binaries instead of glibc ones refused by the runtime)
• •The usage-limit message shown when your monthly spend limit is already used up now also says when your session or weekly limit resets
• •Fixed Bedrock streaming behind proxies that strip the response Content-Type header, which silently doubled billed API calls by re-running every turn non-streaming
• •Fixed Claude Code hanging at startup behind an HTTPS proxy when using Bedrock with an SSO profile and awsAuthRefresh — the credential pre-check now honors HTTPS_PROXY
• •Fixed a raw crash dump when starting Claude Code from a directory that no longer exists; it now prints a clear message
• •Fixed Edit and Write calls pausing for about 5 seconds in JetBrains IDE terminals when the Claude Code plugin is connected
• •Fixed a race where pressing Esc with a prompt queued could let the next turn finish early, leaving the session idle while Claude was still working and letting a later resubmit repeat actions
• •Fixed WebFetch retaining expired page content in memory for the whole session instead of the intended 15 minutes
• •Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) resuming out of plan mode after an idle worker restart
• •Fixed MCP elicitation forms taller than the terminal being clipped in fullscreen mode: the form now fits the window, with hidden fields reachable by scrolling and Accept/Decline always visible
• •Fixed remote MCP servers staying failed after a transient 5xx on a mid-session reconnect in cloud sessions or via SDK setMcpServers()
• •Fixed custom session titles disappearing from /resume after more than ~64 KB of conversation was written following the rename
• •Fixed claude -c/resume picking up sessions from a different directory whose path differed only by characters like _, -, or .
• •Fixed /resume and the agents view showing a session as recently changed (and reordering it) when only its file was touched or it was merely reopened
• •Fixed /resume in all-projects mode telling you to cd into a deleted directory (e.g. a removed worktree); such sessions now resume in the current directory
• •Fixed the dark-ansi theme rendering expanded tool results in fullscreen mode with text the same color as the background
• •Fixed the fullscreen renderer prompt reappearing on every launch when it could never be answered; it now stops after being shown on three launches
• •Fixed .worktreeinclude patterns starting with **/ silently matching nothing when the target lived in a gitignored directory
• •Fixed agents, skills, and commands whose .md file starts with a UTF-8 BOM being silently ignored
• •Fixed /insights echoing literal <message> tags in its response on some models
• •Fixed marketplace metadata.pluginRoot having no effect: bare plugin source names now resolve under it as the docs describe
• •Fixed mouse movement in browser-based terminals inserting text like "35;150;7M" into the prompt when a mouse report arrived split across writes
• •Fixed custom theme overrides for the effort/ultracode status badge colors being ignored
• •Fixed OpenTelemetry trace fragmentation: tool executions deferred by a PreToolUse hook now resume in the original turn's trace instead of starting a new trace
• •Fixed vim mode in the agent view: Escape now switches to NORMAL mode and keeps your text instead of clearing the prompt
• •Fixed the selection:copy keybinding silently dropping a text selection that had been extended with Shift+Arrow keys
• •Fixed the /voice startup tip still appearing after voice dictation was enabled via the voice.enabled setting
• •Fixed shell-mode (!) Tab completion dropping the ./ from a ./script path, which left a command the shell couldn't run
• •Fixed fullscreen mode answering a permission prompt or pressing a button when you clicked the terminal window only to bring it back into focus
• •Fixed slash-command panels (e.g. /config, /model) in fullscreen mode covering the latest messages; the conversation now stays pinned above the panel
• •Fixed the /workflows detail dialog overflowing the terminal and losing its header off-screen when opened while Claude is still responding
• •Fixed the Linux sandbox making a nonexistent .git/config.worktree unreadable, which broke every sandboxed git command in repos with extensions.worktreeConfig set
• •Fixed hooks failing with "posix_spawn ENOENT" after the session's working directory was deleted; they now run from the project root or home directory instead
• •Fixed claudeMdExcludes not excluding a symlinked .claude/rules file when the pattern names the rules directory or the symlink rather than its target
• •Fixed runaway session-title syncing to Remote Control when two Claude Code processes shared one background job's state (2.1.232 regression); title updates are now deduplicated and rate-limited
• •Fixed sessions whose title starts with / being unaddressable by SendMessage and shown as "(untitled)" in ListAgents
• •Fixed Ctrl+W, Ctrl+U, Ctrl+K, Option+Backspace, Option+D and vim df/dt leaving a broken [Pasted text #N] placeholder when the cursor was inside it
• •Fixed masked (password-style) inputs such as the login code field letting their text be pasted back with Ctrl+Y elsewhere or saved to prompt history when cleared with double Esc
• •Fixed Ctrl+Backspace deleting one character instead of a word in search boxes
• •Fixed a request rejected by an organization policy check being re-sent before the rejection was shown
• •Improved the reminder shown after compaction so a skill's original arguments are not re-run as a new request
• •Long file paths on tool-use rows now truncate in the middle to stay on one line
• •Remote sessions keep sending keep-alives while a long SessionStart or Setup hook runs, so the container is not idle-reaped mid-hook
• •/goal: repeat check-ins on long-running background work now back off (30 min, then 1 h, then every 2 h) instead of repeating every 30 minutes
• •/goal: resuming a session from the claude --resume picker now restores its active goal
• •ListAgents now tells a session its own name (the one peers use to message it), and SendMessage to your own name says so instead of "no agent named …"
• •ListAgents and /list-agents now list your live teammates (previously only subagents and other sessions appeared, so a reachable teammate looked absent)
• •keybindingFlavor: "readline" now also matches Bash for word keys: Alt+F and Ctrl/Option+→ stop at the end of the word, Alt+D deletes to it (Ctrl+Y pastes it back), and punctuation separates words
• •Persistent retry mode (CLAUDE_CODE_RETRY_WATCHDOG) now fails immediately on organization spend-limit and out-of-credits errors instead of waiting indefinitely for a reset
• •Claude in Chrome: /clear now closes the session's Chrome tab group, and empty groups are closed on /resume and when Claude Code exits
• •Remote sessions: images uploaded from mobile now include their saved file path, so Claude can copy them into files it creates
• •Claude Code on the web: requests from Bash and other tools to non-API anthropic.com hosts (e.g. www, docs) now go through the session's network proxy, so your environment's allowed domains apply
• •Remote Control: clearer message and claude doctor wording when Remote Control isn't enabled for your account
• •Windows: cross-session messaging is now available, so Claude Code sessions across your machines can message each other with SendMessage and find each other with ListAgents, as on macOS and Linux
• •[VSCode] "View usage" in the usage-limit banner now sits inline with the warning text instead of floating mid-banner

OpenCodev1.18.21Neu

v1.18.21

21. August 2026

• •Continue responses when a model reports an unknown finish reason instead of stopping early
• •Route Vertex AI eu and us multi-region Gemini requests through REP endpoints
• •Keep file search results visible while the next search is loading
• •Register the archive session command in both desktop layouts (@NathanTCode)
• •@NathanTCode:
• •fix(app): register archive session command in both layouts (#41741)

Hermes Agent v0.20.5 (v2026.8.19)

21. August 2026

• •hermes update from an existing install
• •Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

OpenCodev1.18.20Neu

v1.18.20

21. August 2026

• •Surface failed subagent tool calls with a resumable task_id.
• •Retry provider responses that end with finish_reason: network_error.
• •Retry more network error variants, including network-error and network_error.
• •Surface resumable subagent failures instead of returning an empty result.
• •Preserve Cerebras max_completion_tokens without applying an extra output cap.
• •Answer permission requests triggered by subagents during opencode run.
• •Retry xAI capacity and temporary unavailability stream errors.

Codex CLIv0.149.0Neu

0.149.0

20. August 2026

• •Added an interactive codex agents dashboard for searching, starting, opening, renaming, and stopping tasks, with configurable shortcuts. (#39094, #39112, #39114, #39142)
• •Added /cd, /pwd, and /cwd commands for managing the working directory in TUI sessions. (#38894)
• •Added codex queue for sending messages to existing local or remote sessions. (#39092)
• •Expanded Vim editing with character replacement and more change motions such as cw, c$, and cc. (#39661)
• •codex doctor now diagnoses endpoint protection, network/proxy failures, desktop app state, and update connectivity. (#38827, #38918, #39060, #39074)
• •SDK users can now pass exact CLI config overrides and select max or ultra reasoning effort. (#38817, #39662)
• •Queued messages now wake idle sessions reliably, resolve duplicate session names more usefully, and preserve pasted or deferred command semantics. (#39034, #39385, #39604)
• •Resumed and forked threads now restore their active permission profile instead of silently falling back to current defaults. (#39153)

Claude Codev2.1.238Neu

Claude Code 2.1.238

20. August 2026

• •Added a keybindingFlavor setting: set it to "readline" to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default ("classic") is unchanged
• •Plugin marketplaces: headersHelper on a url marketplace or a catalog entry runs a command that mints HTTP headers (e.g. a short-lived token) for catalog and same-origin archive fetches
• •A catalog entry's headersHelper runs only when you install or update that plugin, after its command is shown; claude plugin install/update ask [y/N] (or pass -y)
• •Added claude self-hosted-runner --defer-shutdown-max-min <minutes>: on SIGTERM, keep serving attached sessions, park what is left after that many minutes, then exit
• •Added claude self-hosted-runner --proxy-authorization-command / --proxy-authorization-file for egress proxies that require a freshly issued Proxy-Authorization header on every connection
• •Fixed unbounded memory growth in long interactive sessions: subagent tool results are now released once they leave the recent display window
• •Fixed custom, project, and plugin output styles drifting back to the default voice mid-session
• •Fixed CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION=true not keeping prompt suggestions on when your account is near, but not over, its usage limit
• •Fixed worktree-isolation Bash refusals telling you to remove a redirect when the command had none
• •Fixed self-hosted runners occasionally being removed by the server after a single slow or lost poll request, handing their healthy session to another runner
• •Fixed MCP elicitation dialogs showing nothing for URLs longer than 4,096 characters, and permission prompts dropping the "don't ask again" option when the project path didn't fit the terminal width
• •Fixed leftover /tmp/claude-*-cwd files when a Bash command is killed, times out, or is interrupted
• •Fixed held Backspace being ignored on terminals that send Ctrl+H for Backspace when keystrokes arrive in large bursts (slow SSH/mosh links)
• •Fixed text-wrapping in permission prompt diffs: lines containing wide multi-code-point characters (such as emoji) or tabs are no longer clipped
• •Fixed killing a suspended (Ctrl+Z) session sometimes leaving the terminal in bracketed-paste mode with the cursor hidden
• •Fixed stdio MCP servers receiving a server/discover request before initialize, forcing lazy servers to start their backend on every session open
• •Fixed a proxy's refusal of a connection being reported as a generic network error instead of naming the proxy
• •Fixed the /model and /effort cache-miss warning appearing when the prompt cache had already expired
• •Fixed per-task Stop from the Remote Control tasks panel doing nothing on CLI-hosted sessions
• •Fixed remote sessions exiting when a client delivered a user message without a valid role
• •Fixed Remote Control sessions started by claude remote-control inheriting session-scoped environment variables from the launching shell
• •Fixed a Remote Control session whose process crashed staying unavailable until claude remote-control was restarted; it can now be reused when you next message it
• •Fixed Remote Control messages sent from the web or Desktop while Claude is mid-turn disappearing from the transcript after the turn finishes
• •Fixed Remote Control model picks made on a phone or web not updating the model shown in the terminal
• •Fixed Remote Control disconnecting with "login expired" when a brief network hiccup delays renewing your sign-in; it now retries and stays connected
• •Fixed Remote Control reporting a failed reconnect on sign-out; signing out now ends the session with a clear message
• •Fixed ListAgents/SendMessage reporting "Remote Control is not connected" in sessions run by claude remote-control (server mode) or Desktop/IDE hosts; they now list and reach Remote Control peers
• •Fixed ListAgents and SendMessage exposing the idle worker that the agent view pre-warms for your next background session; it now appears only once a task claims it
• •Cross-session messaging: sending to a session on this machine that refuses inbound messages (e.g. crossSessionInbound: "refuse") now reports "refused" to the sender instead of a silent success
• •Cross-session messaging: a session whose inbox drops your messages (rate limit or full queue) now tells your session, instead of the messages vanishing silently
• •Improved startup: bare claude starts sooner on macOS
• •Improved Bash tool permission checking for zsh-specific syntax in shell conditionals
• •Improved Remote Control connection resilience: brief HTTP 403 refusals from a network edge, VPN, or proxy are now tolerated for up to 3 minutes, with the refusing party named when a block persists
• •Improved startup responsiveness: the automatic update check now runs about 10 seconds after launch instead of competing with startup for CPU
• •Updated the bundled claude-api skill for the Managed Agents Aug 19 release: web search/fetch domain settings and memory stores on self-hosted sandboxes
• •Changed Ctrl+L and Cmd+K in fullscreen to always just repaint — the double-press /clear shortcut was removed, and 1-row nvim terminals no longer trigger automatic /clear loops
• •Changed claude mcp list and claude mcp get to show disabled servers as ⊘ Disabled instead of connecting to them for a health check
• •MCP headersHelper in a project .mcp.json, and inline MCP servers in project or --add-dir agent files, now require that folder's trust dialog to have been accepted (also under claude -p)
• •MCP headersHelper from a project .mcp.json, plugin, or agent file runs without inherited credential env vars; user, managed and claude.ai-scope helpers now run from the Claude config dir

OpenCodev1.18.19Neu

v1.18.19

20. August 2026

• •Added native OpenAI and Anthropic passthroughs for Cloudflare AI Gateway models.
• •Matched Codex rate limits more closely to ChatGPT subscription limits. (@GameOn223)
• •Removed built-in Qwen sampling defaults that could send unsupported settings.
• •Properly show authenticated providers in /connect. (@OpeOginni)
• •Ignore malformed model pricing instead of breaking usage cost calculation.
• •Fall back when OpenAI websocket requests exceed message size limits.
• •Forward ChatGPT workspace compute residency to Codex requests.
• •Updated the default Console URL used by account connection flows.

Antigravityv2.9.1Neu

Remote Control, faster project switching, and more

20. August 2026

• •Introduced Antigravity Remote Control, allowing you to securely connect to and drive agent sessions on your local device from any browser, with proactive push notifications when agents complete tasks or require input.
• •Improved performance across the app: faster startup and project switching, faster loading of conversations with long histories, less lag during active sessions, and smoother opening and collapsing of the sidebar and side panels.
• •Added the ability to collapse top-level sidebar sections. The ungrouped list now shows up to 30 conversations, and conversation actions appear instantly on hover.
• •Notification toasts now appear in the bottom-right corner and collapse into a compact stack that expands on hover, so they no longer cover the screen.
• •Hovering over a file's comment count pill now previews all comments on that file alongside their line numbers, and clicking a comment opens the referenced file, diff, or artifact with that comment focused.
• •Refreshed the Customizations settings screen with collapsible sections and item counts for skills, rules, plugins, and custom agents, consistent back navigation across sub-pages, and clearer card layouts and status indicators for MCP server configurations.
• •Clicking Retry on an agent error card now resumes the task directly, without adding an artificial "Continue" message to your conversation.
• •Custom agents can now reuse the skills, rules, and subagents you already have, using a single inheritCustomizations setting in the agent's frontmatter.

Antigravityv1.1.17Neu

Antigravity CLI: Consolidated agent execution harness and media attachment fixes

20. August 2026

• •Improved the agent execution harness by consolidating onto a single execution path, giving more consistent tool, hook, and prompt behavior.
• •Fixed /teamwork-preview and some other slash commands disappearing for some users.
• •Fixed Enter not opening an active background task or subagent while the prompt was in Vim insert mode.
• •Fixed attaching Ogg audio and video files such as .ogg, .opus and .ogv, which the model rejected because they were sent as the generic application/ogg.

Antigravityv1.1.16Neu

Antigravity CLI: CLI mcp management commands, debounced @ path completion, and MCP resource handling fixes

20. August 2026

• •Added mcp subcommands (add, remove, list, enable, disable) for managing MCP servers in your user-level mcp_config.json without hand-editing it, covering both stdio and HTTP servers through --type, --env and --header.
• •Improved @ file path completion in large workspaces by running the lookup through the bundled ripgrep and debouncing keystrokes, and by ranking a file whose name matches your query above a directory or generated artifact that merely contains it.
• •Improved /effort so it adjusts reasoning effort for Gemini 3.6 Flash and Gemini 3.7 Flash when you sign in with a Gemini API key, a route that previously reported those models as not adjustable even though the same models were adjustable on every other sign-in path.
• •Fixed links printing as raw escape sequences on terminals that do not implement OSC 8 hyperlinks, such as Terminal.app, and extended the same detection to command output and alert bodies, which still emitted hyperlinks unconditionally.
• •Fixed a = character accumulating in the prompt every couple of seconds on terminals that do not implement the Kitty keyboard protocol, where the renderer's periodic re-arming of that protocol was printed as literal text instead of being interpreted.
• •Fixed @ file path completion showing files that were in your .antigravityignore.
• •Fixed the artifact list showing a percent-escaped filename such as quarterly%20plan.md for artifacts whose name contains a space, so the list row, the inline preview and the detail header all spell the name the same way.
• •Fixed the prompt editor's cursor becoming misaligned when text wrapped.

Codex AppNeu

Codex and ChatGPT updates

20. August 2026

• •New features: Apple Messages: Use the Apple Messages plugin to read and search Messages chats on your Mac and prepare or send messages. It’s available on all plans in the ChatGPT desktop app for macOS. You can use the plugin in ChatGPT Work and Codex. By default, ChatGPT sends messages only after you approve the message and its recipients. See the plugin guide for persistent-approval risks, revocation steps, and the known issue with tasks that disable approval prompts.
• •New features: Site co-editing: Where Site collaboration is available, owners can invite active members of the same workspace as editors. Editors can read the Site’s live database data, update the Site, save versions, and publish changes after the owner publishes the Site for the first time. Owners retain control of the audience, settings, analytics, ownership, version restoration, and editor access.
• •New features: Editable Site URLs: Where URL editing is available, owners can change an existing Site’s ChatGPT-hosted address without creating another deployment. The previous address redirects to the new URL. Custom domains are a separate, existing feature and aren’t changed by this setting.
• •New features: Computer History in Europe: Computer History is now available in the EEA, Switzerland, and the United Kingdom for ChatGPT Pro, Business, and Enterprise users in the ChatGPT desktop app on macOS. It’s off by default and requires Memories. Business and Enterprise administrators must enable access before workspace members can choose to turn it on.
• •New features: Shared thread snapshots: On all Codex plans, share a read-only snapshot of a local Codex thread from the ChatGPT desktop app for macOS. The snapshot doesn’t update when the original thread changes. Personal-account links can be opened by anyone with the link; workspace-account links are limited to members of the originating workspace. Codex redacts known secret patterns, but review the shared content because sensitive content may remain. View or revoke links in ChatGPT data controls, under Shared links.
• •New features: Unified pinned threads: Keep the same pinned chats across the ChatGPT desktop app and iOS.

Claude Codev2.1.237Neu

Claude Code 2.1.237

19. August 2026

• •Fixed prompt caching for sessions using an LLM gateway or custom base URL
• •Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work just as thoroughly. Select it under Output style in /config.

Claude Codev2.1.236Neu

Claude Code 2.1.236

19. August 2026

• •Added ANTHROPIC_DEFAULT_MODEL environment variable: sets the model new sessions start on, while a /model pick still overrides it and persists across restarts (unlike ANTHROPIC_MODEL)
• •Added notify_when_idle to cross-session SendMessage: ask another Claude Code session on this machine to send one notice when it next goes idle — opt-in, one-shot, no polling (macOS and Linux)
• •Sandbox: on macOS, wildcard read-deny rules (e.g. **/.env) now take precedence inside allowed read regions, cover matched directories' contents, and can't be bypassed by renaming the denied file
• •Fixed clipboard copy, background housekeeping, background sessions, and local MCP logs breaking after the directory a session had switched into was removed (since 2.1.229)
• •Fixed the fullscreen renderer failing permanently after a single failed start: it now falls back to the classic renderer instead of exiting on every subsequent launch
• •Fixed the /model picker rendering taller than the terminal: it now shows only as many models as fit the window, with the rest reachable by scrolling
• •Fixed SendMessage calls being rejected when a malformed closing tag left the message text inside the summary field
• •Fixed unhandled promise rejections when a subprocess fails to start, for example powershell.exe on WSL with Windows interop disabled (regression in 2.1.234)
• •Fixed fullscreen mode sometimes not showing a newly sent message until the next update after the terminal was resized
• •Fixed a blank band that could remain above the prompt after clearing a multi-line prompt, and panes not repainting after resizing the terminal away and back, in fullscreen mode
• •Fixed the managed-settings approval prompt sometimes not appearing at startup while still capturing the first keypress as approval
• •Fixed terminal tab titles jumping in tmux (iTerm tmux integration): the title is now written only when its text changes instead of animating every 960ms
• •Fixed an unclear error when the cloud environments list came back empty or malformed
• •Fixed the Fable 5 first-time usage-credits prompt auto-selecting the fallback model after 60 seconds with no answer when using Remote Control
• •Fixed spinner tips never appearing, with a repeated background error, when the cached guest-pass reward in ~/.claude.json was malformed
• •Fixed skills hot-reload in SDK/VS Code sessions raising an error on every skills change after the session's working directory was deleted (2.1.229+)
• •Fixed self-hosted runner sessions released on idle, retire, or startup timeout occasionally resuming on another runner before the post-session hook had finished
• •Fixed the Clawd mascot's eyes and feet rendering unevenly in iTerm2 at some font sizes
• •Fixed occasional runaway session recaps: recap text (automatic and /recap) is now capped at 400 characters, cut at a word boundary
• •Improved startup performance: the session counter is now written in the background
• •Improved auto mode: Monitor allow rules are now set aside while auto mode is active, so Monitor commands are reviewed the same way Bash commands are
• •Improved auto mode on Bedrock, Vertex AI, and Foundry, and when telemetry is disabled: the classifier now uses the same defaults as on the Claude API, including severity-scored classification
• •Improved auto mode: the git status check can no longer be fooled by a repo's status.showUntrackedFiles=no setting into reporting a clean tree
• •Changed the /model picker to highlight only the newest model's name, so the highlight marks the new release rather than an arbitrary subset of the list
• •/goal: an idle session whose goal is parked behind long-running background work now checks in automatically after 30 minutes (then 1h, 2h) instead of waiting for you to return
• •/usage now shows the usage-credits spend row for Team and Enterprise members, and shows a capped row at 0% before anything is spent
• •SIGTERM in print/SDK mode no longer records an interrupted turn or synthetic tool denials before exiting; running commands are still terminated and the process still exits with code 143
• •Pressing Enter on a slash-command typo or a command unavailable in this session now reports it instead of running the closest fuzzy match; prefixes and aliases still run
• •Remote Control now marks a session offline within seconds when the CLI exits or its terminal closes
• •SendMessage now refuses further messages to a session up front once a rapid burst would exceed what that session's inbox accepts, instead of reporting them sent while they were dropped
• •Aligned the session title chip on the prompt border with the footer's right edge
• •Right-aligned footer items (goal indicator, session state, background agent status) and truncated notices now share a consistent right margin with the rest of the prompt area
• •[VSCode] Added screen reader support for the transcript: live announcements for replies, permission requests, errors, and status changes, plus per-turn heading navigation

Antigravityv1.1.15Neu

Antigravity CLI: Stream-JSON input mode, markdown agent explicit rules, and startup credential fixes

19. August 2026

• •Added --input-format stream-json to print mode, which reads newline-delimited JSON prompts from stdin and runs one turn per message in a single conversation, so a driver can keep a session open.
• •Added a rules: key to markdown agent frontmatter, so an agent can name rule files directly instead of inheriting your whole rule tree; a rule named this way always applies.
• •Added plugin support for a top-level rules.json, so a plugin can declare the rule files it ships the same way it already declares its skills.
• •Added a more specific hint on the spinner line, which now names the tool call the agent is currently running.
• •Fixed the CLI aborting at startup on hosts that preload their own allocator through LD_PRELOAD, such as Cloud TPU VM images, where it died before the interface appeared.
• •Fixed personal accounts hitting a resource-exhausted error at startup when saved credentials were restored from the system keyring, and cut the repeated account checks that followed.
• •Fixed your billing project, and the license tier it selects, being lost when the CLI restarted and restored saved credentials from the system keyring.
• •Fixed a spurious "Out of credits" message for enterprise users signed in through Application Default Credentials.

Cursor2026-08-19Neu

Cloud Agents and Cursor Harness Improvements

19. August 2026

• •With this release, cloud agents can automatically pick up work in response to events, hold a goal until it's met, and stay on course through long-running sessions.
• •Cursor can now monitor your PRs, watch a Slack thread, or run scheduled tasks. Cursor Agent subscribes to an event source (a thread or conversation) and wakes when something happens. Subscriptions are available for cloud agents only, for now.
• •Cloud agents automatically subscribe to PRs they create and drive them to completion, fixing CI and addressing bot comments. In Slack, ask @cursor check back in an hour and keep going until that feedback is in.
• •Use any skill as a Custom Mode: a skill that stays pinned in the chat. Custom modes keep agents focused on a skill - you can think about it like "always on" skills.
• •From /, pick a skill and press ⌥⏎ (Mac) or Alt+Enter (Windows), or choose Use as Mode.
• •Subagents can now run on their own virtual machines. Each gets an isolated copy of the project with clean context in its own cloud environment.
• •Have subagents test the parent agent's changes in fresh environments or swarm independent fixes without collisions. Try run a swarm of subagents to test my app for bugs, each in its own environment.
• •Use /goal to give the agent a long-lived objective to work towards until it's fully complete.

Codex CLIv0.148.0Neu

0.148.0

18. August 2026

• •Export complete TUI conversations to Markdown with /export, either to the clipboard or a new file. (#37358)
• •Fork sessions with codex exec fork, and archive or restore sessions from the TUI resume picker. (#37367, #37369, #37371)
• •Draft prompts while the TUI initializes, with resume and fork progress shown during startup. (#38642, #38788)
• •View estimated thread credits or cost in /status, status lines, and terminal titles for eligible workspaces. (#38281, #38282)
• •Use Amazon Bedrock Runtime as a built-in provider with AWS profile, region, and GPT-5.6 routing support. (#38470)
• •Hooks can now run commands asynchronously and invoke MCP tools. (#37533, #38705)
• •Model switches and settings updates no longer leave stale instructions behind or change an active turn midstream. (#37260, #38785)
• •Resumed sessions now restore their persisted working directory and approval policy, with more accurate transcript previews. (#37198, #37368, #38605)

Claude Codev2.1.235Neu

Claude Code 2.1.235

18. August 2026

• •Added an optional spellcheck setting that underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell
• •Fixed whole-prompt-cache invalidation when a language server disconnected or reconnected mid-session
• •Fixed nested markdown list items misaligning at depth 3+ and added a hanging indent to wrapped list items in the terminal UI
• •Fixed prompt input highlights (slash commands, keywords, mentions) appearing shifted by one or more characters in some multi-line prompts
• •Fixed Shift+Tab inside the permission prompt's comment field approving the edit and granting session-wide edit permission instead of closing the field
• •Fixed the Agent tool advertising a general-purpose default in sessions where that agent is unavailable: an omitted subagent_type there now gets a clear error listing the available agents
• •Fixed notebook cell delete/replace approval dialogs silently omitting the existing cell content when the notebook or cell could not be read; the dialog now says why
• •Fixed slash commands run while Claude is responding showing HTML entities instead of the actual characters
• •Fixed the prompt footer not showing the "Update installed" restart notice after a background auto-update
• •Fixed the expanded task list (ctrl+t) always starting collapsed when resuming or relaunching into a session that still has open tasks
• •Improved memory and CPU usage while cloud sessions such as /ultrareview or /autofix-pr run in the background — their event streams are no longer re-scanned and re-rendered on every update
• •Improved permission dialogs: display text and "don't ask again" options now always match what a grant would cover, and "don't ask again" is withheld when contents cannot be fully displayed
• •Improved the embedded grep in native macOS/Linux builds: pathological patterns now fail fast instead of exhausting memory, and -m N with -A/-C prints correct context
• •Improved the context-limit error to say when auto-compact is off and point to /config to re-enable it
• •Vim mode: NORMAL mode and cursor position are now preserved when toggling the detailed transcript (ctrl+o) or closing a panel
• •Dialogs: arrow keys and Enter pressed in quick succession now select the option you navigated to instead of the previously highlighted one
• •SendMessage now refuses messages too large for cross-session delivery up front instead of silently dropping them
• •Remote Control: claude rc now applies the same enterprise-gateway availability check as interactive startup
• •[VSCode] Fixed focus jumping between open Claude tabs on its own when a window with several Claude panels is restored or reloaded

Hermes Agent v0.20.4 (2026.8.18)

18. August 2026

• •hermes update from an existing install
• •Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Antigravityv1.1.14

Antigravity CLI: Enterprise sign-in fast path, MCP OAuth metadata documents, /context scrolling, and markdown agent customizations

18. August 2026

• •Added a faster return path for enterprise sign-in, offering returning users a single Continue with ... option naming the authentication method they last used.
• •Added support for OAuth client ID metadata documents when connecting to an MCP server, allowing servers implementing this specification to connect without requiring a manually supplied client ID or dynamic client registration.
• •Improved the /context panel, making it scrollable and dynamically sized to the terminal, with /usage sized the same way.
• •Improved markdown-defined agents with a single inheritCustomizations switch that controls whether an agent adopts skills, rules, plugins, subagents, and MCP servers, replacing inconsistent per-kind defaults.
• •Improved workspace boundary settings: accessing paths outside the workspace now grants read access only, with writes requiring authorization based on the active execution mode.
• •Fixed the CLI exiting silently when its language server failed at startup or during execution; failures are now logged to the terminal and exit with a non-zero status.
• •Fixed sign-in URLs and hyperlinks rendering as garbled escape sequences on terminals that do not support OSC 8 hyperlinks (such as GNU screen), detecting unsupported terminals and rendering plain text instead.
• •Fixed Enter keystrokes being swallowed while the path-suggestion popup was loading, which previously sent the prompt and popped results open above it.

Antigravityv0.1.13

Antigravity IDE: Pre-tool argument modification, synchronous lifecycle hooks, RunCommandConfig timeouts, and step correlation IDs

18. August 2026

• •Pre-Tool Hook Argument Modification: Pre-tool lifecycle hooks can now sanitize, transform, or override tool input arguments before tool execution begins.
• •Synchronous Hook Function Support: Lifecycle hook decorators now accept standard synchronous functions alongside asynchronous coroutines without raising runtime await errors.
• •Structured Command Execution Configuration: Command execution settings are now consolidated under RunCommandConfig, introducing configurable timeouts that default to 10 minutes (600 seconds) alongside daemon execution controls.
• •Tool Lifecycle Step Correlation: ToolResult and ToolExecutionError event payloads now include step_id, enabling end-to-end tracking and correlation of tool invocations across trajectory steps.
• •VS Code Debugging Configuration: Updated setup_vscode_debugging.sh to target the canonical getting_started/hello_world starter example and explicitly configure Gemini Developer API defaults.
• •Synchronous Hook Decorator Execution: Fixed a runtime TypeError when decorating synchronous functions with @pre_turn, @post_tool_call, and other lifecycle hooks by verifying awaitability before awaiting hook responses.
• •LiteRT Early Client Disconnects: Suppressed unhandled ConnectionResetError, ConnectionAbortedError, and BrokenPipeError exceptions when clients disconnect early from local LiteRT server connections.

Droid (Factory AI)v0.199.0

The explorer droid can use every read-only tool, agent questions are easier to answer from the keyboard, and diagrams and long sessions render better in the app

18. August 2026

• •New features: SDK custom system prompts - The TypeScript SDK can now set a custom system prompt for a session, and it is kept when the session resumes
• •New features: Managed BYOK model defaults - Org admins can now pick BYOK custom models as managed defaults for sessions and subagents in Enterprise Controls
• •New features: Service account model policies - Service accounts now appear in Enterprise Controls model policies, so admins can set which models each one may use
• •Improvements: Explorer tool access - The built-in explorer droid can now use every read-only tool, including command execution, web search, and MCP tools, while file edits stay blocked
• •Improvements: Question prompt keyboard controls - You can now pick answers with Space or the number keys, move between questions with Tab, and go back to edit an answer you already gave
• •Improvements: Mermaid diagram rendering - Diagrams in a session now render with the official Mermaid engine, so more diagram types display correctly (app)
• •Improvements: Faster session rendering - Long sessions and streaming command output now render with less lag, so scrolling and typing stay responsive while the agent runs (app)
• •Improvements: Mission model settings - You can now choose the models and reasoning defaults a mission uses from its settings (app)

Hermes Agent v0.20.3 (2026.8.16.2)

17. August 2026

• •hermes update from an existing install
• •Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Claude Codev2.1.234

Claude Code 2.1.234

17. August 2026

• •Added the optional CLAUDE_CODE_PROJECT_DIR_NAME environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory
• •Added the selection:clear keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view
• •Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states
• •Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in /config ("Continue automatically at usage limit")
• •Claude is now told to use your account email only to identify you, and not to send it to unrelated services unless you ask
• •Security: remote file reads, session restore, CLAUDE.md includes, workflow scripts and file uploads now reject Windows NT-namespace (\??\) paths, hardening the remaining pre-approval file accesses against the NTLM credential-leak vector
• •Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted
• •Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts
• •Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field
• •Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences
• •Fixed SendMessage rejecting a recipient copied from ListAgents when the session name is at the 200-character cap or emoji-heavy
• •Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host
• •Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured ${VAR} form, and connection-failure details show only the server origin
• •Fixed strictKnownMarketplaces allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to
• •Fixed modal text such as the /login OAuth URL losing characters when copied in fullscreen
• •Fixed a --- horizontal rule in rendered markdown running into the line after it
• •Fixed consecutive shell commands splitting into multiple "Ran 1 shell command" rows when todo/task updates were interleaved between them
• •Fixed dialogs like /permissions opened while a ! shell command was running being dismissed when the command finished
• •Fixed a queued ! shell command being sent to the model as plain text after pressing up-arrow to edit the queued input
• •Fixed queued messages reappearing in the prompt history while still queued, Esc while selecting a queued message no longer interrupts the turn, and ! mode no longer sticks after a mid-turn submit
• •Fixed accepting the "Try the new fullscreen renderer?" prompt restarting the session without its permission mode (e.g. --dangerously-skip-permissions), tool allow/deny rules, model or effort flags
• •Fixed /tui dropping launch --allowed-tools/--disallowed-tools rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over
• •Fixed trust prompts omitting the repository-wide scope warning when the directory was first seen before the repository existed there
• •Fixed a case where an IDE diff tab closing during a permission re-prompt could answer the new prompt with the previous input
• •Fixed: files sent to the user during Remote Control sessions hosted by Claude Code Desktop or VS Code now upload, so they open on phone and web instead of showing an empty card
• •Fixed: after /login while CLAUDE_CODE_OAUTH_TOKEN is set, the stale-token reminder no longer leaks into Claude's automatically resumed turn — it now appears only to you
• •Fixed: permission previews now relay only to channel servers admitted by the inbound trust gate, and a server's explicit permission-capability opt-out is honored
• •Fixed: credential masking on relayed permission previews can no longer hide commands, paths, or destinations from the approver; oversized private-key blocks now redact under full-strength redaction
• •Fixed: provider API tokens that mask on permission previews now mask even when directly followed by shell delimiters
• •Fixed Claude Desktop inter-session messages being silently dropped by the recipient session when cross-session messaging read as disabled, which left the sender's query "thinking" for many minutes
• •Remote Control: signing this computer in to a different claude.ai account or organization now stops the running session within seconds and says why, instead of a misleading HTTP 404 hours later
• •Remote Control sessions started from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode (and claude.ai/code on the model) as they change
• •Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients
• •SendMessage and ListAgents now say when your account's session list was too long to check completely, instead of treating unseen sessions as absent
• •Expired Anthropic profile credential now points you at /login when a claude.ai login would take precedence
• •Improved the transcript: your own prompts now render markdown (highlighted code blocks, inline code, lists) the same way replies do
• •Improved the "API returned an empty or malformed response" error to say what came back (content type, body kind, size, request ID) and why the original streaming request failed
• •Improved auto-generated session titles to read as short, specific names (e.g. "Login button bug") rather than sentences restating your request (e.g. "Fix the login button on mobile")
• •Reduced the context cost of loading the built-in claude-api skill from ~200k+ tokens to ~25k by loading reference docs on demand
• •/permissions can now be opened while Claude is working — rule changes apply to the rest of the current turn
• •/add-dir <path> can now be used while Claude is working; /add-dir, /autocompact, /theme, /help, /config and /advisor dialogs open mid-turn in the fullscreen TUI
• •/goal now clears itself with a notice when a turn dies on an unrecoverable error (e.g. revoked auth, an exhausted credit balance, or a context overflow) instead of staying armed
• •/goal: when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitely (set CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0 to opt out)
• •claude setup-token now rejects unexpected extra arguments instead of silently ignoring them
• •Changed Esc in fullscreen mode to no longer clear a mouse text selection: it interrupts or dismisses as usual and the selection stays highlighted
• •Removed the redundant "Allowed by auto mode classifier" line that auto mode showed under every Agent tool call
• •Removed the "Default teammate model" setting from /config; agent-team teammates now use the leader's model unless the spawn names one
• •Dimmed the elapsed-time counter on the running tool header so it no longer competes with the bold counts
• •Background task notifications delivered between turns are now sent to the model inside <system-reminder> tags, matching mid-turn delivery
• •Mantle: skip the admin-pin availability probe at startup when a main-loop model is already picked
• •Windows: startup no longer stalls on repeated rename retries when ~/.claude.json is read-only

Cursor2026-08-17

Origin Code Hosting

17. August 2026

• •Origin begins rolling out today in early beta on all paid plans. We're starting with the essentials, designed for agent scale: repos, pull requests, code browsing, and GitHub sync. Agent-native features ship soon.
• •The new Codebase tab is home for Origin repos.
• •Click +New to create a new repo and name it. Once you do, a page shows you how to install the CLI, with commands for how to clone a repo or push a local project. Push, and your code is hosted on Origin.
• •Name your codebase when you create your first repo. That name becomes part of every repo's URL: cursor.com/codebase/acme-corp.
• •Your GitHub repos can sit alongside the ones Cursor hosts. Connect GitHub to Cursor, pick your org, and you'll see the repos you can sync. Select one and Cursor pulls it in. You choose what gets synced and can disconnect a repo at any time. Anyone with read or write access to a synced repo can view it in Cursor too.
• •Synced repos update in real time. Browse, search, and pull from the copy in Origin. Pushes keep going to GitHub, which stays the source of truth for anything started there. Icons next to each repo name tell you which ones Cursor hosts and which came from GitHub.
• •Every repo has pull requests. Open one to see the timeline, commits, checks, and files changed. Review the diff, leave comments, and merge.
• •Pull requests on synced repos sync both ways: comment in Cursor and it posts to GitHub, react or reply on GitHub and it shows up in Cursor within seconds. Got a review assigned to you on GitHub? Review and merge it from Cursor.

Droid (Factory AI)v0.198.0

Diff lines wrap by default, plus fixes for diff search, the model selector, empty sessions, and mission models

17. August 2026

• •Improvements: Diff line wrapping - Long lines in a diff now wrap by default so you can read them without scrolling sideways (app)
• •Improvements: Clearer empty response error - When a model finishes without producing an answer, the message now explains why and suggests retrying or switching models
• •Bug fixes: Diff search navigation - Stepping to the next or previous diff search match now scrolls to it instead of stopping when the match is still loading (app)
• •Bug fixes: Model selector search - The model selector keeps focus in its search box so your typing is no longer lost while filtering models (app)
• •Bug fixes: Chat activity while thinking - The chat keeps showing the running tool while the agent is thinking instead of clearing it (app)
• •Bug fixes: Empty draft sessions - Sessions that were opened but never used no longer pile up in your session list and resume picker
• •Bug fixes: Missions after sleep - A mission now moves a stuck worker onto a fresh one after your machine sleeps instead of hanging
• •Bug fixes: Mission model defaults - A mission now starts with the mission models from your defaults, and every connected client shows the models the run is actually using

Hermes Agent v0.20.2 (2026.8.16)

16. August 2026

• •hermes update from an existing install
• •Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

OpenClaw2026.8.1-beta.2

OpenClaw 2026.8.1-beta.2

15. August 2026

• •Secret egress host binding: bind each shared-store secret to exact HTTPS destination hosts across CLI, Gateway RPC, and Control UI so unbound sentinel substitution fails closed before plaintext egress. Thanks @shakkernerd.
• •GPT-5.6 Ultra and runtime switching: support Sol, Terra, and Luna across OpenClaw and Codex engines; keep model, runtime, and thinking selection atomic through /model and fallback; and add live matrix coverage for both harnesses. Thanks @anyech and @vincentkoc.
• •Channel plugin ingress monitors: add a shared plugin SDK monitor for durable admission, polling, pruning, claim identity validation, adoption handoff, and shutdown, and migrate IRC, Synology Chat, and Google Chat to the shared lifecycle. Thanks @vincentkoc and @shakkernerd.
• •SQLite snapshots: add openclaw backup sqlite create|list|verify|restore for compact, verified global and per-agent database artifacts with fresh-target-only restore. Thanks @giodl73-repo.
• •macOS app profiles: isolate named app instances across state, preferences, Keychain, Gateway services, and duplicate-instance ownership while keeping host-global login and node services untouched. Thanks @shakkernerd and @vincentkoc.
• •Plugin install provenance warnings: require explicit --force acknowledgement for arbitrary executable plugin sources in CLI and chat installs, keep trusted ClawHub, bundled, official-catalog, and tracked-update flows frictionless, and restrict Crestodian installs to trusted sources. Thanks @jesse-merhi and @vincentkoc.
• •Control UI update recovery: the "A new version is available" Reload button now waits out the gateway restart that stranded the chunk and reloads as soon as it answers, instead of silently doing nothing and leaving a manual hard reload as the only way out. Thanks @vincentkoc.
• •Secret egress host binding: bind each shared-store secret to exact HTTPS destination hosts across CLI, Gateway RPC, and Control UI so unbound sentinel substitution fails closed before plaintext egress. Thanks @shakkernerd.

Droid (Factory AI)v0.197.0

More accurate voice dictation and steadier option navigation in prompts

15. August 2026

• •Improvements: Voice dictation accuracy - Voice dictation now transcribes what you say more accurately (app)
• •Bug fixes: Prompt option navigation - Moving through the options in a question or permission prompt no longer jumps to whichever option the mouse is resting on (app)

Claude Codev2.1.233

Claude Code 2.1.233

14. August 2026

• •Added GitLab merge request URL support to the --worktree flag and the claude agents view (where MRs display as !N)
• •Added an opt-in forward_user_identity apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user
• •Added opt-in memory cgroup support for Bash tool commands on Linux (CLAUDE_CODE_TOOL_MEMORY_LIMIT) so a runaway build can't stall the session
• •Added CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS environment variable to configure the WebFetch session URL cache TTL (default unchanged: 15 minutes)
• •Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt
• •Fixed MCP v2 connections endlessly reopening the subscriptions/listen stream against servers that terminate long-held streams on a fixed timeout (e.g. serverless hosts)
• •Fixed Notification hooks not firing for permission prompts when running under Claude Desktop or VS Code
• •Fixed idle sessions on Linux sometimes keeping one CPU core at 100% when sandboxing is enabled
• •Fixed bundled skill aliases like /checkup and /review reporting "Unknown command" in -p mode or with plugins/MCP loaded when a user or project skill shadows the bundled skill
• •Fixed skill/command argument substitution to prevent argument values from being re-expanded as template markers
• •Fixed Windows paths spelled with the NT \??\ device prefix bypassing UNC path validation, closing an NTLM credential-leak vector
• •Improved claude self-hosted-runner session start time: the session branch is now created without rewriting the working tree, and two server round trips no longer block the agent's launch
• •Improved apps gateway error forwarding: 400/413 errors from Vertex, Foundry, and Claude Platform on AWS upstreams now carry the upstream's own message; fixes a bug with auto-compact on apps gateway
• •Improved claude plugin validate to check a bare .claude/skills directory, reporting SKILL.md files whose frontmatter fails to parse
• •Improved screen reader mode: the /effort selector renders as a numbered list with a typed-number prompt, and hint and dialog text is no longer clipped
• •Improved print mode diagnostics: a [claude-code:unrecognized_model] line is written to stderr when a request goes out for a model ID Claude Code doesn't recognize; map it with modelOverrides to silence
• •Changed the GitHub app setup tip to no longer appear in repositories whose origin remote is on gitlab.com or bitbucket.org; the enterprise marketplace tip now covers non-GitHub internal git hosts
• •Todo/task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) are no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models; set CLAUDE_CODE_ENABLE_TODO_TOOLS=1 to bring them back
• •Windows: fixed auto mode repeatedly stopping for manual approval on ordinary cd <dir> && <command> > file Bash commands (a 2.1.232 regression)
• •Reverted the 2.1.232 Bash permission changes for Cygwin-style symlinks on Windows and for input redirections (< file); a narrower version will return in a later release

Antigravityv1.1.13

Antigravity CLI: GEMINI_API_KEY authentication, custom agent task management, embedded ripgrep caching, and conversation database fixes

14. August 2026

• •Added support for GEMINI_API_KEY, allowing the CLI to run directly against the Gemini API without signing in. Set modelProvider: "gemini" in settings.json, export GEMINI_API_KEY, and optionally configure GOOGLE_GEMINI_BASE_URL for custom endpoints. The banner and /help show Gemini API key as the credential, and /logout explains that it originates from the environment.
• •Improved /codesearch resilience by falling back to a local search when the ripgrep binary cannot be executed, such as when blocked by endpoint security software.
• •Improved artifact list scrolling performance by caching each file's preview line count instead of re-reading every listed file from disk on every keypress.
• •Improved custom agent support by making manage_task available to declarative agents that have not opted out of fundamental components, enabling custom agents to list and kill background tasks, with clearer step descriptions like Killed task X and Checked task X.
• •Improved search_web step visualization by displaying the query while the search is in progress rather than only after completion.
• •Improved agent behavior after backgrounding tasks by removing anti-polling reminder text from manage_task and manage_inbox tool responses to prevent unintended polling loops.
• •Improved the /resume picker by clearly relabeling its second tab.
• •Improved deleting conversations in the /resume picker by remapping the shortcut from ctrl+delete to f4 for reliable cross-platform terminal compatibility on macOS.

Droid (Factory AI)v0.196.0

Forking now keeps you in your current session and credit usage moves to its own page, plus fixes for the pull request indicator, SessionStart hook context, and credit rates for two models

14. August 2026

• •Improvements: Fork stays in place - Forking a session now keeps you in the original session and prints a resume command you can use to open the copy
• •Improvements: Credit usage page - Credit usage now has its own page instead of living inside Analytics (app)
• •Bug fixes: Pull request indicator - The linked pull request indicator stays visible when a status lookup briefly fails instead of disappearing
• •Bug fixes: SessionStart hook context - Context added by a SessionStart hook is kept for the session instead of being dropped
• •Bug fixes: Model credit rates - Credit usage for Grok 4.5 and GPT-5.3-Codex fast mode is now reported at the correct rate

Hermes Agent v0.20.1 (2026.8.13)

13. August 2026

• •Existing installs: hermes update
• •Fresh install: see the installer one-liner in the README

OpenCodev1.18.18

v1.18.18

13. August 2026

## Core ### Bugfixes - Select the Kimi system prompt correctly for official Moonshot and Kimi providers - Fix xhigh reasoning effort for xai models

Antigravityv2.8.1

Chat Responsiveness Improvements

13. August 2026

• •Improved responsiveness and reduced hanging issues when sending messages to the agent.

Antigravityv2.5.5

Antigravity SDK: Windows Media Attachments and Chat Responsiveness Improvements

13. August 2026

• •Fixed an issue where the agent failed when attaching images or media files on Windows machines.
• •Improved responsiveness and reduced hanging issues when sending messages to the agent.

Antigravityv0.1.12

Antigravity IDE: Fix proto deserialization regression for ActionGenerateImage output paths

13. August 2026

• •ActionGenerateImage Proto Skew: Resolved client-side deserialization errors where the bundled binary emitted ActionGenerateImage.output_path while the shipped Python proto lacked the corresponding field, ensuring robust protobuf parsing across image generation steps.